US7336842B2 - Method and apparatus for generating data representative of features of an image - Google Patents
Method and apparatus for generating data representative of features of an image Download PDFInfo
- Publication number
- US7336842B2 US7336842B2 US10/470,285 US47028503A US7336842B2 US 7336842 B2 US7336842 B2 US 7336842B2 US 47028503 A US47028503 A US 47028503A US 7336842 B2 US7336842 B2 US 7336842B2
- Authority
- US
- United States
- Prior art keywords
- dct
- image
- sign
- face
- signs
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related, expires
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B42—BOOKBINDING; ALBUMS; FILES; SPECIAL PRINTED MATTER
- B42D—BOOKS; BOOK COVERS; LOOSE LEAVES; PRINTED MATTER CHARACTERISED BY IDENTIFICATION OR SECURITY FEATURES; PRINTED MATTER OF SPECIAL FORMAT OR STYLE NOT OTHERWISE PROVIDED FOR; DEVICES FOR USE THEREWITH AND NOT OTHERWISE PROVIDED FOR; MOVABLE-STRIP WRITING OR READING APPARATUS
- B42D25/00—Information-bearing cards or sheet-like structures characterised by identification or security features; Manufacture thereof
- B42D25/20—Information-bearing cards or sheet-like structures characterised by identification or security features; Manufacture thereof characterised by a particular use or purpose
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/169—Holistic features and representations, i.e. based on the facial image taken as a whole
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
- G06T9/007—Transform coding, e.g. discrete cosine transform
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B42—BOOKBINDING; ALBUMS; FILES; SPECIAL PRINTED MATTER
- B42D—BOOKS; BOOK COVERS; LOOSE LEAVES; PRINTED MATTER CHARACTERISED BY IDENTIFICATION OR SECURITY FEATURES; PRINTED MATTER OF SPECIAL FORMAT OR STYLE NOT OTHERWISE PROVIDED FOR; DEVICES FOR USE THEREWITH AND NOT OTHERWISE PROVIDED FOR; MOVABLE-STRIP WRITING OR READING APPARATUS
- B42D25/00—Information-bearing cards or sheet-like structures characterised by identification or security features; Manufacture thereof
- B42D25/30—Identification or security features, e.g. for preventing forgery
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Definitions
- the present invention relates to a device and a method to make the identification signal of the image feature and, more particularly to a device and a method to make the identification signal of the image feature that can make the image data volume smaller by using the DCT sign characteristic of arbitrary signals including images, and also can be applied to a new type of passport, credit card, driver's license, or ID card that is hard to forge by displaying a face photograph and the bar code corresponding to the face photograph to lead to a great contribution to the overall security system.
- the identification by a person's face has so far been made at various places to prevent a suspicious individual from entering the building or premises or to confirm whether the bearer of a passport is a true person.
- a person is authenticated by comparing the person's face with the face image such as an affixed photo or database registered in advance.
- the face image of the person to be authenticated must be input into the computer, and the concerned persons face must be compared by the computing algorithm with the face image registered in advance.
- the processing speed for face identification is dependent on calculating time on computer, therefore, if the data volume used in the database was reduced greatly, the speed of processing would be faster, and the data volume to be used for registering would be also smaller.
- the traditional image data is huge in volume, it is problematic that it takes much time to compare and identify the image data, and a very big capacity is required for registering database.
- One of the purposes of the present invention is to provide a device and a method to make an identification signal of the image feature with a small volume of database by using DCT sign characteristic of arbitrary signals including the image.
- Another purpose of the present invention is to provide a device and a method to make the identification signal of the image feature applicable to a new type of passport, credit card, driver's license, or ID card that is hard to forge by displaying a face photograph and the bar code corresponding to the face photograph to lead to a great contribution to the overall security system, and also to provide passports, credit cards, driver's licenses, and ID cards produced by means of the said device and the method.
- FIG. 1 is a block diagram showing an embodiment of the device to make the identification signal of the image feature in accordance with the present invention
- FIG. 2 is a detailed block diagram illustrating an embodiment of the image input part in accordance with the present invention.
- FIG. 3 shows the image by 8 ⁇ 8 pixels
- FIG. 4 is a cubic chart illustrating the relationship between the amplitude and the position of the coefficient after DCT conversion shown in FIG. 3 is made;
- FIG. 5 shows the original photographs
- FIG. 6 shows the images in which the two-dimension DCT taken from the original photographs shown in FIGS. 5 ( a ) and ( b ) have let the DCT signs exchanged;
- FIG. 6 ( a ) is a combination of the DCT amplitude of a dome and the DCT signs of a woman;
- FIG. 6 ( b ) is an opposite combination of the DCT amplitude of a woman and the DCT signs of a dome;
- FIGS. 7 ( a ), ( b ), ( c ) show the original pictures of a dome, a human face, and plant leaves respectively.
- FIGS. 7 ( a ′), ( b ′), ( c ′) show the SOS images corresponding to FIGS. 7 ( a ), ( b ), ( c ) respectively;
- FIG. 8 is the AOS of the human face picture shown in FIG. 7 ( b );
- FIG. 9 shows unique patterns taken by the DCT signs, depending on each original image
- FIG. 10 is a plan of FIG. 4 projected from right above, in which black circles show “ ⁇ ” signs and white circles show “+” signs;
- FIG. 11 shows a map for taking out the sign made from the average value of DCT sign amplitudes of a lot of people's face images
- FIG. 12 shows the positions where the signs should be taken out, whereas the positions are illustrated as circles on white backgrounds that are obtained by laying the map of FIG. 11 on FIG. 10 ;
- FIG. 13( a ) shows the image of the object
- FIG. 13( b ) shows the DCT signs of the object image
- FIG. 13( c ) shows the object image bar-coded
- FIG. 14 shows the positions of the DCT sign after DCT transformation has been made.
- the present invention will next be described in detail by means of an example of the device to make the identification signal of the image feature according to the present invention.
- 1 is an image input part
- 2 is a DCT conversion part where the data of an input image is transformed into a two-dimension discrete cosine transform (DCT) signal
- 3 is an extracting part where the features of the above-mentioned image data are extracted based on the information provided by a DCT sign extraction information providing part 4
- 5 is a one-dimension binary signal composing part where one-dimension binary signals are composed of the DCT signs of the said extracted data.
- the image input part 1 consists of a picture-taking means 100 taking picture of a subject, an image capturing and processing part 101 capturing necessary images, and a pixel number setting part 102 .
- a digital camera can be used as a picture taking means 100 for example.
- a digital camera will shoot subjects such as the face of a person or the face photo of a person through its photograph lens, form their images on the photographing face of CCD (photograph devices), and photoelectrically transform the optical images formed by the CCD into signal charge corresponding to the amount of light in the unit of pixel.
- the signals photoelectrically transformed is input into the image processing part, where noise is lowered, gain etc. is adjusted, and the said signals are converted into digital signals by an A/D converter.
- the digital camera can be replaced by a scanner-registering part 103 .
- the data registered is a multi-valued digital data.
- the multi-valued digital data obtained from the digital camera 100 or the scanner-registering part 103 is sent to the image capturing and processing part 101 that captures necessary parts of the images. It is preferable that only a face image is captured as for a portrait, though shoulders part may be included.
- the pixel number setting part 102 the pixel number such as N ⁇ N pixels is set up. N differs according to objects; it takes 32, 64, 128, 256, or 512.
- the DCT conversion part 2 the two-dimension DCT part
- the data of input image is transformed into the two-dimension DCT signs. Because of its characteristic of developing real numbers by even function, DCT is very useful for compressing the image.
- DCT coefficient
- the amplitude of DCT made from Fourier transform has a characteristic similar to Fourier transform (though, of course, not in strictly mathematical terms). In a word it can be said that the DCT amplitude holds the information on the energy of an original image signal.
- FIG. 6( a ) is a combination of the woman's DCT signs and the DCT amplitude of the dome.
- FIG. 6( b ) is a combination of DCT signs of the dome and the woman's DOCT amplitude. It is obvious that FIG. 6( a ) is a woman's photograph, and no piece of the look of the dome is found.
- FIG. 6( b ) is an image from the photograph of the dome, and no piece of the woman's face is found. Therefore, it can be said that the DCT sign has the information constituting the framework of the signal when the signal is composed.
- the DCT sign plays a predominant role in the re-composition of a signal.
- Sign-only synthesis also called SOS
- Sign-only synthesis is defined by the following equation according to the aforementioned equations (2) and (4):
- ⁇ uv is defined by the equation (5), that is, it is equal to the inverse-transform equation 2, where all the amplitude
- FIG. 7 shows an example of sign-Only synthesis.
- FIGS. 7 ( a ), ( b ), ( c ) are the original images of the dome, the person's face, and the leaves of the plant respectively
- FIGS. 7 ( a ′), ( b ′), ( c ′) are the SOS images corresponding to the dome, the person's face, and the leaves of the plant respectively. This makes it clear that the SOS image is correspondent one-on-one to the original image from the viewpoint of the image recognition.
- AOS Amplitude-only synthesis
- FIG. 8 shows the AOS for the person's face image of FIG. 7( b ).
- the AOS being black, it is almost useless as an image.
- FIG. 9 shows that the DCT signs take unique patterns, depending on each original image.
- the DCT sign of an arbitrary signal including the image substantially corresponds one-on-one with an original signal, and its inverse-transform (Sign-only synthesis) becomes just like the second difference value.
- a signal is an image
- its Sign-only synthesis clearly expresses the silhouette line of the image
- the Sign-only synthesis can be treated as equivalent to an original signal. That is, this means that the original image can be treated as equivalent to the DCT sign (one bit of plus or minus).
- the DCT conversion part 2 in the present invention decides the plus and minus signs as shown in FIG. 10 (the white circles represent a positive sign, and black circles represent a negative sign in the figure), in case, for instance, the DCT coefficient is obtained as shown in FIG. 4 by transforming an image by DCT as shown in FIG. 3 . That is, the distribution of positive and the negative signs shown in FIG. 10 can be obtained by extracting only positive and the negative signs from DCT conversion coefficient shown in FIG. 4 having the positive and the negative signs as well as the volume.
- the DCT conversion part 2 can indicate the feature of the image, using only a small volume of information, by deciding the positive and negative signs after obtaining DCT sign of the image.
- the feature of the image can be shown based on even smaller volume of information, since parts effective for showing the feature are extracted by means of a method described later based on the information (DCT sign extraction information) provided by the DCT sign extraction information providing part 4 in the extraction part 3 by the method as described later.
- the DCT sign extraction information is obtained from the DCT average amplitude of a lot of object images or the DCT amplitude size of one object image. That is, the DCT sign extraction information providing part 4 provides the information determined from the size of full picture DCT average amplitude of a lot of object images or the size of DCT amplitude for one object image.
- the information determined from the DCT average amplitude of a lot of object images or the DCT amplitude size of one object image is to be decided in advance by the following methods before each of the devices according to the present invention is produced.
- the position having important information that is, the positions of the large amplitude are extracted.
- the positions in which the signs are extracted are decided from those averages, and this positions are taken as the information provided by the DCT sign extraction information providing part 4 .
- the face image of each person is transformed into DCT signals, and then the positions holding important information, i.e. the positions of large amplitude are extracted, and the positions in which the signs are extracted are decided. These positions are taken as the information provided by the DCT sign extraction information providing part 4 .
- the information decided depending on the latter method is provided from the DCT sign extraction information providing part 4 .
- the information decided as above-mentioned offers information on which sign of the position, i.e., which frequency is to be extracted, which sign of the position, i.e., which frequency is not to be extracted.
- FIG. 11 is the information provided by the DCT sign extraction information providing part, in which the positions of white squares show where the sign should be extracted, and the positions of black background show where the positions are not extracted.
- the sign is extracted based on the information provided by the DCT sign extraction information providing part 4 by comparing the information provided by the DCT sign extraction information providing part 4 as shown in FIG. 12 . Extraction may be made by scanning lines, for instance, from the top left square frame position toward the right one by one on FIG. 12 , and signals obtained may be composed as a row of one-dimension binary signals.
- the form of the information provided by the DCT sign extraction information providing part 4 is not limited to the form shown in FIG. 11 . There is no limitation on the form of the information, as far as the information shows the frequency position to be extracted. Therefore, the information can be the progression showing the frequency position to be extracted.
- one-dimension binary information is built in the one-dimension binary signal composing part 5 .
- a very simple and short one-dimension binary signal of a image can be composed, if only the sign for the part characterizing the signal is taken out in the extraction part 3 where the feature of the above-mentioned image data is extracted based on the information provided by the DCT sign extraction information providing part 4 , and is reconstructed as a one-dimension signal in the one-dimension binary signal composing part 5 in the order determined beforehand (for instance, by scanning).
- the information of the one-dimension binary can be obtained by making a one-dimension binary signal having, for instance, two binaries of “1” and “0” based on the assumption of 1 as the positive sign and 0 as the negative sign.
- a one-dimension binary signal makes handling easy, if computerization is introduced. It is even more desirable to have a bar-coding means 6 that bar-codes the information obtained in the one-dimension binary signal composing part. If the information gets bar-coded, recognition of difference in images, pattern matching, etc. can be made at high speed. This is a very big advantage.
- the feature of the face image can often be identified by extracting information existing in a comparatively low frequency part, since information for identifying the person's face appears in the comparatively low frequency part.
- the N ⁇ N size image shown in FIG. 13( a ) is transformed by the Full picture DCT, and only the positive and negative signs of the information transformed by DCT are extracted, the positive and negative information on the DCT sign of the same size with the N ⁇ N size two-dimension signal (image) shown in FIG. 13( b ) can be obtained.
- FIG. 14 shows the positions of the signs shown in FIG. 13( b ), and especially, the shaded portion in FIG. 4 shows the low frequency part. Scanning of the positive and negative sign information of DCT sign shown in FIG. 13( b ) from top to bottom, and from left to right can constitute one-dimension binary signals. Moreover, the + (white) and ⁇ (black) bar code can also be made. FIG. 13( c ) shows the resultant bar code. Thus, the person's face can be identified by the sign of the low frequency field. Though the number of signs is decided by the number of image pixel in FIG.
- the person's face can be identified by smaller number of signs, if only the low frequency part that is the pixels strongly showing the feature on average in the area is used.
- taking, for instance, 500 pixels of the image makes it possible to display 2500 different human faces.
- 600-1000 image pixels are normally taken, therefore, 2 600 ⁇ 1000 different persons' faces can be displayed, which means that infinite number of persons' faces can actually be handled.
- the feature of the image is extracted in the extracting part 3 by using the DCT sign extraction information offered from the DCT sign extraction information providing part 4 , however, even if neither the extracting part 3 nor the DCT sign extraction information providing part 4 exists, the purpose of this invention can be achieved by extracting only the DCT coefficient signs transformed in the DCT transform part 2 , and composing the one-dimension binary signal in the one-dimension binary signal composing part 5 based on the sign (DCT sign) of the DCT coefficient for only extracting the sign of DCT coefficient.
- the bar code obtained from the device and method to make the identification signal of the image feature according to the present invention can be used together with a face photo, or independently to make passports, credit cards, driver's licenses, or ID cards.
- the present invention makes it possible to provide a device and a method to make the identification signal of the image feature by using the character of DCT sign of an arbitrary signal including the image, applicable to a face photo and the corresponding bar code to be affixed on a new type of passport, credit card, certificate, ID card, etc that are hard to forge to lead to a great contribution to the overall security system.
- the present invention will contribute to the police agency, airport, etc that must identify a face targeted from among a lot of personal faces in a short period of time, which is very important for such special workplaces.
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Discrete Mathematics (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
- Collating Specific Patterns (AREA)
- Credit Cards Or The Like (AREA)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2001367829 | 2001-11-30 | ||
JP2001-367829 | 2001-11-30 | ||
PCT/JP2002/011095 WO2003049028A1 (fr) | 2001-11-30 | 2002-10-25 | Appareil et procede de generation de signaux d'identification caracteristiques d'une image |
Publications (2)
Publication Number | Publication Date |
---|---|
US20040234131A1 US20040234131A1 (en) | 2004-11-25 |
US7336842B2 true US7336842B2 (en) | 2008-02-26 |
Family
ID=19177523
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/470,285 Expired - Fee Related US7336842B2 (en) | 2001-11-30 | 2002-10-25 | Method and apparatus for generating data representative of features of an image |
Country Status (9)
Country | Link |
---|---|
US (1) | US7336842B2 (fr) |
EP (1) | EP1450301A4 (fr) |
JP (1) | JP3860811B2 (fr) |
KR (1) | KR20040058117A (fr) |
CN (1) | CN1327391C (fr) |
AU (1) | AU2002336313A1 (fr) |
CA (1) | CA2449049A1 (fr) |
HK (1) | HK1069912A1 (fr) |
WO (1) | WO2003049028A1 (fr) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080260199A1 (en) * | 2004-08-13 | 2008-10-23 | Ingenia Technology Limited | Authenticity Verification Methods, Products and Apparatuses |
US20080294900A1 (en) * | 2004-08-13 | 2008-11-27 | Ingenia Technology Limited | Authenticity Verification of Articles Using a Database |
US20100316251A1 (en) * | 2005-12-23 | 2010-12-16 | Ingenia Holdings Limited | Optical Authentication |
US8078875B2 (en) | 2005-07-27 | 2011-12-13 | Ingenia Holdings Limited | Verification of authenticity |
US8421625B2 (en) | 2004-03-12 | 2013-04-16 | Ingenia Holdings Limited | System and method for article authentication using thumbnail signatures |
US8615475B2 (en) | 2008-12-19 | 2013-12-24 | Ingenia Holdings Limited | Self-calibration |
US8682076B2 (en) | 2008-12-19 | 2014-03-25 | Ingenia Holdings Limited | Signature generation for use in authentication and verification using a non-coherent radiation source |
US8699088B2 (en) | 2004-03-12 | 2014-04-15 | Ingenia Holdings Limited | Methods and apparatuses for creating authenticatable printed articles and subsequently verifying them |
US8892556B2 (en) | 2009-11-10 | 2014-11-18 | Ingenia Holdings Limited | Optimisation |
US9818249B1 (en) | 2002-09-04 | 2017-11-14 | Copilot Ventures Fund Iii Llc | Authentication method and system |
CN111881708A (zh) * | 2019-05-03 | 2020-11-03 | 爱唯秀股份有限公司 | 人脸识别系统 |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4011362B2 (ja) * | 2002-02-15 | 2007-11-21 | 浩 近藤 | パスポートの偽造防止情報作成システム、パスポート及び偽造パスポート検出システム |
CN101819631B (zh) * | 2010-04-16 | 2012-12-26 | 深圳大学 | 一种身份识别方法和身份识别系统 |
US9027099B1 (en) | 2012-07-11 | 2015-05-05 | Microstrategy Incorporated | User credentials |
US9887992B1 (en) * | 2012-07-11 | 2018-02-06 | Microstrategy Incorporated | Sight codes for website authentication |
US8775807B1 (en) | 2012-10-26 | 2014-07-08 | Microstrategy Incorporated | Credential tracking |
US9640001B1 (en) | 2012-11-30 | 2017-05-02 | Microstrategy Incorporated | Time-varying representations of user credentials |
US9154303B1 (en) | 2013-03-14 | 2015-10-06 | Microstrategy Incorporated | Third-party authorization of user credentials |
CN105162686B (zh) * | 2015-08-03 | 2016-05-04 | 福建北卡科技有限公司 | 基于图媒介的多形态即时信息隐密通信方法与系统 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5241600A (en) * | 1991-07-16 | 1993-08-31 | Thinking Machines Corporation | Vertification system for credit or bank card or the like |
US5466918A (en) * | 1993-10-29 | 1995-11-14 | Eastman Kodak Company | Method and apparatus for image compression, storage, and retrieval on magnetic transaction cards |
US5636292A (en) * | 1995-05-08 | 1997-06-03 | Digimarc Corporation | Steganography methods employing embedded calibration data |
JP2001052142A (ja) | 1999-08-06 | 2001-02-23 | Toshiba Corp | Idカード、idカード発行装置ならびにidカード認証装置 |
US6373891B1 (en) * | 1997-07-02 | 2002-04-16 | Klaus Schulze | System and method for image sequence processing |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07121626B2 (ja) * | 1989-12-25 | 1995-12-25 | 大日本印刷株式会社 | Idカードの偽造防止加工処理方法および偽造防止idカード |
US5505494B1 (en) * | 1993-09-17 | 1998-09-29 | Bell Data Software Corp | System for producing a personal id card |
ES2105936B1 (es) * | 1994-03-21 | 1998-06-01 | I D Tec S L | Perfeccionamientos introducidos en la patente de invencion n. p-9400595/8 por: procedimiento biometrico de seguridad y autentificacion de tarjetas de identidad y de credito, visados, pasaportes y reconocimiento facial. |
CN1085591C (zh) * | 1995-02-24 | 2002-05-29 | 黄金富 | 多特征身份证 |
US7216232B1 (en) * | 1999-04-20 | 2007-05-08 | Nec Corporation | Method and device for inserting and authenticating a digital signature in digital data |
-
2002
- 2002-10-25 CA CA002449049A patent/CA2449049A1/fr not_active Abandoned
- 2002-10-25 WO PCT/JP2002/011095 patent/WO2003049028A1/fr active Application Filing
- 2002-10-25 AU AU2002336313A patent/AU2002336313A1/en not_active Abandoned
- 2002-10-25 CN CNB028110137A patent/CN1327391C/zh not_active Expired - Fee Related
- 2002-10-25 JP JP2003550148A patent/JP3860811B2/ja not_active Expired - Fee Related
- 2002-10-25 KR KR10-2003-7016117A patent/KR20040058117A/ko not_active Application Discontinuation
- 2002-10-25 EP EP02770273A patent/EP1450301A4/fr not_active Withdrawn
- 2002-10-25 US US10/470,285 patent/US7336842B2/en not_active Expired - Fee Related
-
2005
- 2005-03-15 HK HK05102258A patent/HK1069912A1/xx not_active IP Right Cessation
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5241600A (en) * | 1991-07-16 | 1993-08-31 | Thinking Machines Corporation | Vertification system for credit or bank card or the like |
US5466918A (en) * | 1993-10-29 | 1995-11-14 | Eastman Kodak Company | Method and apparatus for image compression, storage, and retrieval on magnetic transaction cards |
US5636292A (en) * | 1995-05-08 | 1997-06-03 | Digimarc Corporation | Steganography methods employing embedded calibration data |
US5636292C1 (en) * | 1995-05-08 | 2002-06-18 | Digimarc Corp | Steganography methods employing embedded calibration data |
US6373891B1 (en) * | 1997-07-02 | 2002-04-16 | Klaus Schulze | System and method for image sequence processing |
JP2001052142A (ja) | 1999-08-06 | 2001-02-23 | Toshiba Corp | Idカード、idカード発行装置ならびにidカード認証装置 |
Non-Patent Citations (4)
Title |
---|
Ching-Yung Lin, et al.; "A Robust Image Authentication Method Distinguishing JPEG Compression from Malicious Manipulation", IEEE Transactions on Circuits and Systems of Video Technology, vol. 11, No. 2, Feb. 2001. |
Gary L. Friedman, et al.; "The Trustworthy Digital Camera: Restoring Credibility to the Photographic Image"; IEEE Transactions on Consumer Electronics, vol. 39, Nov. 1993, No. 4, New York, US. |
Hiroshi Kondo, et al.; "Identification of DCT Signs for Sub-Block Coding"; International Symposium on Signal Processing and its Applications (ISSPA), Kuala Lumpur, Malaysia, Aug. 13-16, 2001. |
Machine Translation of 2001-52142 cited in applicant's informaiton disclosure. * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9818249B1 (en) | 2002-09-04 | 2017-11-14 | Copilot Ventures Fund Iii Llc | Authentication method and system |
US8699088B2 (en) | 2004-03-12 | 2014-04-15 | Ingenia Holdings Limited | Methods and apparatuses for creating authenticatable printed articles and subsequently verifying them |
US8757493B2 (en) | 2004-03-12 | 2014-06-24 | Ingenia Holdings Limited | System and method for article authentication using encoded signatures |
US9019567B2 (en) | 2004-03-12 | 2015-04-28 | Ingenia Holdings Limited | Methods and apparatuses for creating authenticatable printed articles and subsequently verifying them |
US8896885B2 (en) | 2004-03-12 | 2014-11-25 | Ingenia Holdings Limited | Creating authenticatable printed articles and subsequently verifying them based on scattered light caused by surface structure |
US8421625B2 (en) | 2004-03-12 | 2013-04-16 | Ingenia Holdings Limited | System and method for article authentication using thumbnail signatures |
US8766800B2 (en) | 2004-03-12 | 2014-07-01 | Ingenia Holdings Limited | Authenticity verification methods, products, and apparatuses |
US8502668B2 (en) | 2004-03-12 | 2013-08-06 | Ingenia Holdings Limited | System and method for article authentication using blanket illumination |
US8749386B2 (en) | 2004-03-12 | 2014-06-10 | Ingenia Holdings Limited | System and method for article authentication using signatures |
US20080260199A1 (en) * | 2004-08-13 | 2008-10-23 | Ingenia Technology Limited | Authenticity Verification Methods, Products and Apparatuses |
US20080294900A1 (en) * | 2004-08-13 | 2008-11-27 | Ingenia Technology Limited | Authenticity Verification of Articles Using a Database |
US8103046B2 (en) * | 2004-08-13 | 2012-01-24 | Ingenia Holdings Limited | Authenticity verification of articles using a database |
US8078875B2 (en) | 2005-07-27 | 2011-12-13 | Ingenia Holdings Limited | Verification of authenticity |
US8497983B2 (en) | 2005-12-23 | 2013-07-30 | Ingenia Holdings Limited | Optical authentication |
US20100316251A1 (en) * | 2005-12-23 | 2010-12-16 | Ingenia Holdings Limited | Optical Authentication |
US8615475B2 (en) | 2008-12-19 | 2013-12-24 | Ingenia Holdings Limited | Self-calibration |
US8682076B2 (en) | 2008-12-19 | 2014-03-25 | Ingenia Holdings Limited | Signature generation for use in authentication and verification using a non-coherent radiation source |
US8892556B2 (en) | 2009-11-10 | 2014-11-18 | Ingenia Holdings Limited | Optimisation |
CN111881708A (zh) * | 2019-05-03 | 2020-11-03 | 爱唯秀股份有限公司 | 人脸识别系统 |
US11176394B2 (en) * | 2019-05-03 | 2021-11-16 | Ulsee Inc. | Face image processing method and device |
Also Published As
Publication number | Publication date |
---|---|
CN1531709A (zh) | 2004-09-22 |
EP1450301A1 (fr) | 2004-08-25 |
CA2449049A1 (fr) | 2003-06-12 |
CN1327391C (zh) | 2007-07-18 |
JP3860811B2 (ja) | 2006-12-20 |
JPWO2003049028A1 (ja) | 2005-04-21 |
US20040234131A1 (en) | 2004-11-25 |
EP1450301A4 (fr) | 2005-08-17 |
HK1069912A1 (en) | 2005-06-03 |
AU2002336313A1 (en) | 2003-06-17 |
WO2003049028A1 (fr) | 2003-06-12 |
KR20040058117A (ko) | 2004-07-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7336842B2 (en) | Method and apparatus for generating data representative of features of an image | |
US7174044B2 (en) | Method for character recognition based on gabor filters | |
EP3035236A1 (fr) | Code quadridimensionnel, et système et procédé de reconnaissance d'image basée sur un code quadridimensionnel, et système et procédé d'extraction | |
CN110490214B (zh) | 图像的识别方法及系统、存储介质及处理器 | |
CN101373514A (zh) | 人脸识别方法和系统 | |
KR102145132B1 (ko) | 딥러닝을 이용한 대리 면접 예방 방법 | |
CN112085094B (zh) | 单证图像翻拍检测方法、装置、计算机设备和存储介质 | |
Goljan | Blind detection of image rotation and angle estimation | |
KR20120060424A (ko) | 정합대상영상의 정합판정방법 | |
Mehta et al. | Near-duplicate image detection based on wavelet decomposition with modified deep learning model | |
CN107025435B (zh) | 一种人脸识别处理方法和系统 | |
Samal | Minimum resolution for human face detection and identification | |
WO2021192216A1 (fr) | Système d'identification d'objet individuel | |
JP5279007B2 (ja) | 照合システム、照合方法、プログラム及び記録媒体 | |
CN111767845B (zh) | 证件识别方法及装置 | |
JP4011362B2 (ja) | パスポートの偽造防止情報作成システム、パスポート及び偽造パスポート検出システム | |
Paul et al. | A study on image enhancement techniques for fingerprint identification | |
Kanchana et al. | Quadtree decomposition for palm print feature representation in palmprint recognition system | |
Vasudevan et al. | A basic study of image processing and its application areas | |
CN113221830B (zh) | 一种超分活体识别方法、系统、终端及存储介质 | |
Mohan et al. | A tenable approach for protection of electronic medical records using thermal image watermarking | |
JP2003237264A (ja) | Idカード、及びidカード作成装置、照合システム | |
Veličković et al. | The Watermark Applications in Multimodal Biometric Identification | |
Desachy | Texture features in remote sensing imagery | |
Habib | Iris Anti-Spoofing Using Image Quality Measures |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: GLOBAL SECURITY DESIGN, INC., JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:KONDO, HIROSHI;REEL/FRAME:014939/0077 Effective date: 20030718 Owner name: KONDO, HIROSHI, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:KONDO, HIROSHI;REEL/FRAME:014939/0077 Effective date: 20030718 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY Free format text: PAYER NUMBER DE-ASSIGNED (ORIGINAL EVENT CODE: RMPN); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
FPAY | Fee payment |
Year of fee payment: 4 |
|
AS | Assignment |
Owner name: ACS CO., LTD., JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GLOBAL SECURITY DESIGN, INC.;KONDO, HIROSHI;REEL/FRAME:029388/0495 Effective date: 20121126 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
FEPP | Fee payment procedure |
Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
LAPS | Lapse for failure to pay maintenance fees |
Free format text: PATENT EXPIRED FOR FAILURE TO PAY MAINTENANCE FEES (ORIGINAL EVENT CODE: EXP.); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
STCH | Information on status: patent discontinuation |
Free format text: PATENT EXPIRED DUE TO NONPAYMENT OF MAINTENANCE FEES UNDER 37 CFR 1.362 |
|
FP | Lapsed due to failure to pay maintenance fee |
Effective date: 20200226 |